def plot_ROC(to_detect, to_learn, expected, noise, outfile, coefficient=None, radius=None):
to_learn_sites = CD.ObservedSites()
read_proto_from_file(to_learn_sites, to_learn)
expected_sites = CD.ObservedSites()
read_proto_from_file(expected_sites, expected)
print "number of expected_sites"
print len(expected_sites.site)
to_detect_sites = CD.ObservedSites()
read_proto_from_file(to_detect_sites, to_detect)
noise_sites = CD.ObservedSites()
read_proto_from_file(noise_sites, noise)
filt_to_detect_sites = remove_noise(to_detect_sites, noise_sites)
filt_to_learn_sites = remove_noise(to_learn_sites, noise_sites)
expected_set = sites_name_set(expected_sites)
"""
Following are Stratified-K-Fold.
"""
kfold = 5
total_site_name_list = list()
to_detect_sites_map = dict()
for site in filt_to_detect_sites.site:
total_site_name_list.append(site.name)
to_detect_sites_map[site.name] = site
to_learn_sites_map = dict()
for site in filt_to_learn_sites.site:
to_learn_sites_map[site.name] = site
# prepare the train and test
to_detect_sites_list = list()
to_learn_sites_list = list()
Y = list()
for name in total_site_name_list:
to_detect_sites_list.append(to_detect_sites_map[name])
to_learn_sites_list.append(to_learn_sites_map[name])
if name in expected_set:
Y.append(1)
else:
Y.append(0)
to_detect_sites_list = np.array(to_detect_sites_list)
to_learn_sites_list = np.array(to_learn_sites_list)
Y = np.array(Y)
skf = StratifiedKFold(Y, kfold)
# scan the parameters and output the FPR and TPR
params = dict()
params['train_inconsistent'] = coefficient[0]
params['test_inconsistent'] = coefficient[1]
# params['test_diameter'] = radius[0]
outf = open(outfile, 'a')
for r in np.arange(radius[0], radius[1], 1):
tpr = np.zeros(5, dtype=np.float)
fpr = np.zeros(5, dtype=np.float)
params['test_diameter'] = r
count = 0
for train, test in skf:
print "train size: {0}, test size: {1}".format(len(train),
len(test))
learn_train, learn_test = to_learn_sites_list[train], to_learn_sites_list[test]
detect_train, detect_test = to_detect_sites_list[train], to_detect_sites_list[test]
y_train, y_test = Y[train], Y[test]
estimator = Estimator(filt_to_detect_sites.config)
estimator.score(learn_test, detect_test, y_test, params)
tpr[count] = estimator.rate[0]
fpr[count] = estimator.rate[1]
count += 1
res_str = ",".join([ str(params["train_inconsistent"]),
str(params["test_inconsistent"]),
str(params["test_diameter"]) ]) + "\n"
res_str += ",".join([ str(tpr.mean()), str(fpr.mean()) ]) + "\n"
outf.write(res_str)
def integrated_plot_ROC(text_input, text_train, dom_input, dom_train, expected, noise, outfile,
c_text_train, c_text_test, c_dom_train, c_dom_test,
r_text_start, r_text_end, r_dom_start, r_dom_end):
text_to_learn_sites = CD.ObservedSites()
read_proto_from_file(text_to_learn_sites, text_train)
dom_to_learn_sites = CD.ObservedSites()
read_proto_from_file(dom_to_learn_sites, dom_train)
expected_sites = CD.ObservedSites()
read_proto_from_file(expected_sites, expected)
print "number of expected_sites"
print len(expected_sites.site)
text_to_detect_sites = CD.ObservedSites()
read_proto_from_file(text_to_detect_sites, text_input)
dom_to_detect_sites = CD.ObservedSites()
read_proto_from_file(dom_to_detect_sites, dom_input)
noise_sites = CD.ObservedSites()
read_proto_from_file(noise_sites, noise)
filt_text_to_detect_sites = remove_noise(text_to_detect_sites, noise_sites)
filt_text_to_learn_sites = remove_noise(text_to_learn_sites, noise_sites)
filt_dom_to_detect_sites = remove_noise(dom_to_detect_sites, noise_sites)
filt_dom_to_learn_sites = remove_noise(dom_to_learn_sites, noise_sites)
expected_set = sites_name_set(expected_sites)
"""
Following are Stratified-K-Fold.
"""
kfold = 5
total_site_name_list = list()
text_to_detect_sites_map = dict()
for site in filt_text_to_detect_sites.site:
total_site_name_list.append(site.name)
text_to_detect_sites_map[site.name] = site
text_to_learn_sites_map = dict()
for site in filt_text_to_learn_sites.site:
text_to_learn_sites_map[site.name] = site
dom_to_detect_sites_map = dict()
for site in filt_dom_to_detect_sites.site:
dom_to_detect_sites_map[site.name] = site
dom_to_learn_sites_map = dict()
for site in filt_dom_to_learn_sites.site:
dom_to_learn_sites_map[site.name] = site
# prepare the train and test
text_to_detect_sites_list = list()
text_to_learn_sites_list = list()
dom_to_detect_sites_list = list()
dom_to_learn_sites_list = list()
Y = list()
for name in total_site_name_list:
text_to_detect_sites_list.append(text_to_detect_sites_map[name])
text_to_learn_sites_list.append(text_to_learn_sites_map[name])
dom_to_detect_sites_list.append(dom_to_detect_sites_map[name])
dom_to_learn_sites_list.append(dom_to_learn_sites_map[name])
if name in expected_set:
Y.append(1)
else:
Y.append(0)
text_to_detect_sites_list = np.array(text_to_detect_sites_list)
text_to_learn_sites_list = np.array(text_to_learn_sites_list)
dom_to_detect_sites_list = np.array(dom_to_detect_sites_list)
dom_to_learn_sites_list = np.array(dom_to_learn_sites_list)
Y = np.array(Y)
skf = StratifiedKFold(Y, kfold)
# scan the parameters and output the FPR and TPR
text_params = dict()
text_params['train_inconsistent'] = c_text_train
text_params['test_inconsistent'] = c_text_test
dom_params = dict()
dom_params['train_inconsistent'] = c_dom_train
dom_params['test_inconsistent'] = c_dom_test
# params['test_diameter'] = radius[0]
outf = open(outfile + "_text_r_" + str(r_text_start), 'a')
for t_r in np.arange(r_text_start, r_text_end, 1):
text_params['test_diameter'] = t_r
for d_r in np.arange(r_dom_start, r_dom_end, 1):
dom_params['test_diameter'] = d_r
tpr = np.zeros(5, dtype=np.float)
fpr = np.zeros(5, dtype=np.float)
count = 0
for train, test in skf:
print "train size: {0}, test size: {1}".format(len(train),
len(test))
text_learn_train, text_learn_test = text_to_learn_sites_list[train], text_to_learn_sites_list[test]
text_detect_train, text_detect_test = text_to_detect_sites_list[train], text_to_detect_sites_list[test]
dom_learn_train, dom_learn_test = dom_to_learn_sites_list[train], dom_to_learn_sites_list[test]
dom_detect_train, dom_detect_test = dom_to_detect_sites_list[train], dom_to_detect_sites_list[test]
y_train, y_test = Y[train], Y[test]
text_estimator = Estimator(filt_text_to_detect_sites.config)
text_estimator.score(text_learn_test, text_detect_test, y_test, text_params)
dom_estimator = Estimator(simhash_config = filt_dom_to_detect_sites.config,
cloaking_sites = text_estimator.cloaking_sites)
dom_estimator.score(dom_learn_test, dom_detect_test, y_test, dom_params)
tpr[count] = dom_estimator.rate[0]
fpr[count] = dom_estimator.rate[1]
count += 1
res_str = ",".join([ str(dom_params["train_inconsistent"]),
str(dom_params["test_inconsistent"]),
str(dom_params["test_diameter"]) ]) + "\n"
res_str += ",".join([ str(tpr.mean()), str(fpr.mean()) ]) + "\n"
outf.write(res_str)
def cross_validation(to_detect, to_learn, expected, noise, outfile, coefficient=None, radius=None):
to_learn_sites = CD.ObservedSites()
read_proto_from_file(to_learn_sites, to_learn)
expected_sites = CD.ObservedSites()
read_proto_from_file(expected_sites, expected)
print "number of expected_sites"
print len(expected_sites.site)
to_detect_sites = CD.ObservedSites()
read_proto_from_file(to_detect_sites, to_detect)
noise_sites = CD.ObservedSites()
read_proto_from_file(noise_sites, noise)
filt_to_detect_sites = remove_noise(to_detect_sites, noise_sites)
filt_to_learn_sites = remove_noise(to_learn_sites, noise_sites)
expected_set = sites_name_set(expected_sites)
"""
Following are Stratified-K-Fold.
"""
kfold = 5
total_site_name_list = list()
to_detect_sites_map = dict()
for site in filt_to_detect_sites.site:
total_site_name_list.append(site.name)
to_detect_sites_map[site.name] = site
to_learn_sites_map = dict()
for site in filt_to_learn_sites.site:
to_learn_sites_map[site.name] = site
# prepare the train and test
to_detect_sites_list = list()
to_learn_sites_list = list()
Y = list()
for name in total_site_name_list:
to_detect_sites_list.append(to_detect_sites_map[name])
to_learn_sites_list.append(to_learn_sites_map[name])
if name in expected_set:
Y.append(1)
else:
Y.append(0)
to_detect_sites_list = np.array(to_detect_sites_list)
to_learn_sites_list = np.array(to_learn_sites_list)
Y = np.array(Y)
skf = StratifiedKFold(Y, kfold)
scores = list()
best_params = list()
for train, test in skf:
print "train size: {0}, test size: {1}".format(len(train),
len(test))
learn_train, learn_test = to_learn_sites_list[train], to_learn_sites_list[test]
detect_train, detect_test = to_detect_sites_list[train], to_detect_sites_list[test]
y_train, y_test = Y[train], Y[test]
estimator = Estimator(filt_to_detect_sites.config, outfile, coefficient, radius)
estimator.fit(learn_train, detect_train, y_train)
best_params.append(estimator.best_params)
scores.append(estimator.score(learn_test, detect_test, y_test))
# filt_cloaking_sites = remove_noise(both_detected, noise_sites)
# cross_val_score(svc, X_digits, y_digits, cv=kfold, n_jobs=-1)
print "best_parameters"
print best_params
print scores